OpenAI’s New Agent Stack: Computer Use, Decisions API, UltraFast, Dots—Ari Weinstein & Nikunj Handa

Computer use agents have reached a performance milestone where they now execute software tasks faster than the average human, transitioning from simple automation to complex, multi-step debugging and execution. Recent advancements, including the introduction of the Decisions API and updates to the Agents API, enable faster, parallel inference and more fluid, event-driven interactions. By leveraging accessibility metadata and direct DOM access, these agents move beyond basic screen-scraping to perform sophisticated operations like software development and testing. Infrastructure improvements, such as async tool calling, mid-turn steering, and extended 12-hour caching guarantees, significantly reduce latency and operational costs. These developments empower developers to build persistent, real-time agents capable of delegating intricate tasks—from meal prep customization to complex API-less web interactions—while maintaining high reliability and efficiency in the software development lifecycle.